
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import squarify


column_names = ['State_Name', 'District_Name', 'Crop_Year', 'Season', 'Crop', 'Area(ha)', 'Production(tonne)']


df = pd.read_csv('crop_production.csv', names = column_names)
df

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\IPython\core\interactiveshell.py:3441: DtypeWarning: Columns (2,5,6) have mixed types.Specify dtype option on import or set low_memory=False.
  exec(code_obj, self.user_global_ns, self.user_ns)


df.drop(0, inplace = True)
df.head(25)


df.reset_index(drop=True, inplace=True)
df


df[df['Season'] == 'Kharif']


df[df['Season'] == 'Rabi']


df[df['Season'] == 'Winter']


df.dtypes

State_Name           object
District_Name        object
Crop_Year            object
Season               object
Crop                 object
Area(ha)             object
Production(tonne)    object
dtype: object


df['Area(ha)'] = df['Area(ha)'].astype(float)
df['Production(tonne)'] = df['Production(tonne)'].astype(float)

df.dtypes

State_Name            object
District_Name         object
Crop_Year             object
Season                object
Crop                  object
Area(ha)             float64
Production(tonne)    float64
dtype: object


df.describe()


districts_count_per_state = df.groupby(['State_Name'], as_index = False)['District_Name'].count()
districts_count_per_state


districts_count_per_state.rename(columns = {'District_Name':'District_Count'}, inplace = True)
districts_count_per_state


districts_count_per_state.sort_values('District_Count', ascending = False, inplace = True)
districts_count_per_state


label = districts_count_per_state['State_Name'][:20]
sizes = districts_count_per_state['District_Count']

plt.figure(figsize= (20, 10))
squarify.plot(sizes = sizes, label = label, alpha = .8)
plt.axis('off')

(0.0, 100.0, 0.0, 100.0)


indexNames = df[df['Season'] == 'Whole Year '].index
df_without_whole_year = df.drop(indexNames)
df_without_whole_year


total_amount_crops_produced_per_state = df_without_whole_year.groupby(['State_Name'], as_index = False)['Production(tonne)'].sum()
total_amount_crops_produced_per_state


fig = px.bar(total_amount_crops_produced_per_state, x='State_Name', y='Production(tonne)', title='Total amount yield for each state')
fig.update_layout(barmode='group')
fig.show()


amount_crops_produced_per_season = df.groupby(['Season'], as_index = False)['Production(tonne)'].sum()
amount_crops_produced_per_season


amount_crops_produced_per_season.iloc[4, 0]

'Whole Year '


df.Season = df.Season.str.rstrip()


df.iloc[3, 3]

'Whole Year'


amount_crops_produced_per_season = df.groupby(['Season'], as_index = False)['Production(tonne)'].sum()
amount_crops_produced_per_season


#Either one of the codes below can be used in removing the specified value whole year
# amount_crops_produced_per_season.drop([0, 4], axis = 0, inplace = True)
# amount_crops_produced_per_season


indexNames = amount_crops_produced_per_season[amount_crops_produced_per_season['Season'] == 'Whole Year'].index
amount_crops_produced_per_season.drop(indexNames , inplace=True)
amount_crops_produced_per_season


amount_crops_produced_per_season.describe()


def format_number(data_value, indx):
    if data_value >= 1000000:
        formatter = '{:1.1f}M'.format(data_value*0.000_001)
    else:
        formatter = '{:1.0f}K'.format(data_value*0.001)
    return formatter


fig, ax = plt.subplots(figsize=(15,6))

ax.barh(amount_crops_produced_per_season['Season'], amount_crops_produced_per_season['Production(tonne)'])
ax.set_xlabel('Total amount of Crops produced(tonne)')
ax.set_ylabel('Crop production seasons')
ax.set_title('Total amount of crops produced per season')
ax.xaxis.set_major_formatter(format_number)
plt.show()


indexNames = df[df['Season'] == 'Whole Year'].index
df.drop(indexNames , inplace=True)
df


crop_year_per_prod = df.groupby(['Crop_Year'], as_index = False)['Production(tonne)'].sum()
crop_year_per_prod


crop_year_per_prod.head(10).dtypes

Crop_Year             object
Production(tonne)    float64
dtype: object


crop_year_per_prod.tail(10).dtypes

Crop_Year             object
Production(tonne)    float64
dtype: object


crop_year_per_prod['Crop_Year'].unique()

array([1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007,
       2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, '1997', '1998',
       '1999', '2000', '2001', '2002', '2003', '2004', '2005', '2006',
       '2007', '2008', '2009', '2010', '2011', '2012', '2013', '2014'],
      dtype=object)


df['Crop_Year'] = df['Crop_Year'].astype(int)


df['Crop_Year'].unique()

array([2000, 2001, 2002, 2003, 2004, 2005, 2010, 2006, 1997, 1998, 1999,
       2007, 2008, 2009, 2011, 2012, 2013, 2014, 2015])


amount_crops_produced_per_year = df.groupby(['Crop_Year'], as_index = False)['Production(tonne)'].sum()
amount_crops_produced_per_year


fig, ax = plt.subplots(figsize=(15,6))

ax.plot(amount_crops_produced_per_year['Crop_Year'], amount_crops_produced_per_year['Production(tonne)'], marker = "o",)
ax.set_ylabel('Total amount of Crops produced(tonne)')
ax.set_xlabel('Crop production year')
ax.set_title('Total amount of crops produced per year')
ax.yaxis.set_major_formatter(format_number)

plt.show()


crops_total_amount_produced_each_year = df.groupby(['Crop_Year', 'Crop'], as_index = False)['Production(tonne)'].sum()
crops_total_amount_produced_each_year


all_years = crops_total_amount_produced_each_year['Crop_Year'].unique()

for year in all_years:
    fig, ax = plt.subplots(figsize=(20,6))
    index = crops_total_amount_produced_each_year[crops_total_amount_produced_each_year['Crop_Year'] == year]
    test = index[index['Production(tonne)'] <= 99999]
    ax.bar(test['Crop'], test['Production(tonne)'])
    ax.yaxis.set_major_formatter(format_number)
    ax.set_title(year)
    plt.show()


for year in all_years:
    index = crops_total_amount_produced_each_year[crops_total_amount_produced_each_year['Crop_Year'] == year]
    fig = px.bar(index, x='Crop', y='Production(tonne)', title=f'Crop year {year}')
    fig.update_layout(barmode='group')
    fig.show()


for year in all_years:
    index = crops_total_amount_produced_each_year[crops_total_amount_produced_each_year['Crop_Year'] == year]
    test = index[index['Production(tonne)'] <= 99999]
    fig = px.bar(test, x='Crop', y='Production(tonne)', title=f'Crop year {year}')
    fig.update_layout(barmode='group')
    fig.show()


crop_count_df = df.groupby(['Crop'])['Crop'].count()
# converting grouped series to a dataframe
crop_count_df = crop_count_df.to_frame()

# renaming crop count column form crop to crop_count
crop_count_df.rename(columns = {'Crop' : 'Crop_Count'}, inplace = True)

# resetting the index of the dataframe to move the index from crop 
crop_count_df = crop_count_df.reset_index()


crop_count_df


ordered_crop_count = crop_count_df.sort_values(by = 'Crop_Count', ascending = False)
ordered_crop_count = ordered_crop_count.reset_index()


ordered_crop_count


plt.figure(figsize=(18,12))
sns.barplot("Crop","Crop_Count",data=crop_count_df).set(title='Crop count')
plt.xticks(rotation=90)
plt.show()

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


top_25_crops = ordered_crop_count.head(25)
top_25_crops


plt.figure(figsize=(18,12))
sns.barplot("Crop","Crop_Count",data=top_25_crops).set(title = 'The 25 most popular crops')
plt.xticks(rotation=90)
plt.show()

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


label = ordered_crop_count['Crop'][:25]
sizes = ordered_crop_count['Crop_Count']

plt.figure(figsize= (18, 10))
squarify.plot(sizes = sizes, label = label, alpha = .8)
plt.axis('off')

(0.0, 100.0, 0.0, 100.0)


least_25_crops = ordered_crop_count.tail(25)
least_25_crops


plt.figure(figsize=(18,12))
sns.barplot('Crop', 'Crop_Count', data = least_25_crops).set(title='The 25 least popular crops')
plt.xticks(rotation=90)
plt.show()

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


top_25_crops = ordered_crop_count['Crop'].head(25)
all_crops = top_25_crops.unique()
all_crops

array(['Rice', 'Maize', 'Moong(Green Gram)', 'Urad', 'Groundnut',
       'Sesamum', 'Wheat', 'Rapeseed &Mustard', 'Arhar/Tur', 'Gram',
       'Jowar', 'Bajra', 'Sunflower', 'Small millets',
       'Peas & beans (Pulses)', 'Linseed', 'Masoor', 'Cotton(lint)',
       'Barley', 'Ragi', 'Horse-gram', 'Other Kharif pulses',
       'Other  Rabi pulses', 'Castor seed', 'Soyabean'], dtype=object)


for crop in all_crops:
    crop_df = df[df['Crop'] == crop]
    crop_df = crop_df.groupby(['Season'], as_index = False)['Production(tonne)'].sum()
    fig, ax = plt.subplots(figsize=(15,5))
    sns.barplot('Season', 'Production(tonne)', data = crop_df).set(title= crop)
    ax.yaxis.set_major_formatter(format_number)
    plt.show()

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\seaborn\_decorators.py:36: FutureWarning:

Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.


for crop in all_crops:
    crop_df = df[df['Crop'] == crop]
    crop_df = crop_df.groupby(['Season'], as_index = False)['Production(tonne)'].sum()
    fig = px.bar(crop_df, x='Season', y='Production(tonne)', title=f'Crop {crop}')
    fig.update_layout(barmode='group')
    fig.show()


weather_seasons = {'Autumn': 'Autumn', 'Kharif':'Autumn', 'Rabi': 'Winter', 'Summer': 'Summer', 'Winter': 'Winter'}

df['Weather_Seasons'] = df['Season'].apply(lambda x: weather_seasons[x])


crop_count_df = df.groupby(['Crop', 'Weather_Seasons'])['Crop'].count()
crop_count_df = crop_count_df.to_frame()


crop_count_df


crop_count_df.rename(columns = {'Crop':'Crop_Count'}, inplace = True)


crop_count_df = crop_count_df.reset_index()
crop_count_df


crop_max_df = crop_count_df.groupby(['Crop'])['Crop_Count'].max()


crop_max_df = crop_max_df.to_frame()
crop_max_df


crop_max_df = crop_max_df.reset_index()
crop_max_df


crop_count_merged = pd.merge(crop_count_df, crop_max_df)
crop_count_merged


crop_type = {'Autumn': 'Kharif',  'Summer': 'Zaid', 'Winter': 'Rabi'}

crop_count_merged['Crop_Type'] = crop_count_merged['Weather_Seasons'].apply(lambda x: crop_type[x])
crop_count_merged


crop_count_merged.drop(['Weather_Seasons'], axis = 1, inplace = True)


df = pd.merge(df, crop_count_merged, how = 'left')
df


df.drop(['Season'], axis = 'columns', inplace = True)
df.drop(['Crop_Count'], axis = 'columns', inplace = True)

df


crop_prod_per_season_df = pd.DataFrame()
for crop in all_crops:
    crop_df = df[df['Crop'] == crop]
    crop_df = crop_df.groupby(['Weather_Seasons', 'Crop'], as_index = False)['Production(tonne)'].sum()
    crop_prod_per_season_df = crop_prod_per_season_df.append(crop_df)
    fig = px.bar(crop_df, x='Weather_Seasons', y='Production(tonne)', title =f'{crop}')
    fig.update_layout(barmode='group')
    fig.show()


fig = px.bar(crop_prod_per_season_df, x='Weather_Seasons', y='Production(tonne)', color='Crop')
fig.update_layout(barmode = 'group')
fig.show()


crop_prod_inmill_per_season_df = crop_prod_per_season_df[crop_prod_per_season_df['Production(tonne)'] <= 9999999]


fig = px.bar(crop_prod_inmill_per_season_df, x='Weather_Seasons', y='Production(tonne)', color='Crop')
fig.update_layout(barmode = 'group')
fig.show()


crop_prod_inth_per_season_df = crop_prod_per_season_df[crop_prod_per_season_df['Production(tonne)'] <= 999999]


fig = px.bar(crop_prod_inth_per_season_df, x='Weather_Seasons', y='Production(tonne)', color='Crop')
fig.update_layout(barmode = 'group')
fig.show()


total_amount_of_crops_per_state = df.groupby(['State_Name', 'Crop'], as_index = False)['Production(tonne)'].sum()
total_amount_of_crops_per_state


all_states = total_amount_of_crops_per_state['State_Name'].unique()
all_states

array(['Andaman and Nicobar Islands', 'Andhra Pradesh',
       'Arunachal Pradesh', 'Assam', 'Bihar', 'Chandigarh',
       'Chhattisgarh', 'Dadra and Nagar Haveli', 'Goa', 'Gujarat',
       'Haryana', 'Himachal Pradesh', 'Jammu and Kashmir ', 'Jharkhand',
       'Karnataka', 'Kerala', 'Madhya Pradesh', 'Maharashtra', 'Manipur',
       'Meghalaya', 'Mizoram', 'Nagaland', 'Odisha', 'Puducherry',
       'Punjab', 'Rajasthan', 'Sikkim', 'Tamil Nadu', 'Telangana ',
       'Tripura', 'Uttar Pradesh', 'Uttarakhand', 'West Bengal'],
      dtype=object)


for state in all_states:
    index = total_amount_of_crops_per_state[total_amount_of_crops_per_state['State_Name'] == state]
    fig = px.bar(index, x='Crop', y='Production(tonne)', title=state)
    fig.update_layout(barmode='group')
    fig.show()


for state in all_states:
    index = total_amount_of_crops_per_state[total_amount_of_crops_per_state['State_Name'] == state]
    test = index[index['Production(tonne)'] <= 999999]
    fig = px.bar(test, x='Crop', y='Production(tonne)', title=state)
    fig.update_layout(barmode='group')
    fig.show()


area_prod = df.groupby(['Area(ha)', 'Crop_Type'], as_index = False)['Production(tonne)'].sum()
area_prod


top_30_area_prod = area_prod.head(30)
top_30_area_prod.rename(columns = {'Production(tonne)':'Total_Production(tonne)'}, inplace = True)

C:\Users\mikos\AppData\Local\Programs\Python\Python39\lib\site-packages\pandas\core\frame.py:5034: SettingWithCopyWarning:


A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy


top_30_area_prod


fig = px.scatter(top_30_area_prod, x='Area(ha)', y='Total_Production(tonne)', color = 'Crop_Type', 
                 title = 'Graph showing ')
fig.update_layout(barmode = 'group')
fig.show()


crop_type_produced_per_state = df.groupby(['State_Name', 'Area(ha)', 'Crop_Type'], as_index = False)['Production(tonne)'].sum()
crop_type_produced_per_state


for state in all_states:
    index = crop_type_produced_per_state[crop_type_produced_per_state['State_Name'] == state]
    fig = px.scatter(index, x='Area(ha)', y='Production(tonne)', color='Crop_Type')
    fig.show()


for state in all_states:
    index = crop_type_produced_per_state[crop_type_produced_per_state['State_Name'] == state]
    test = index[index['Production(tonne)'] <= 999]
    fig = px.scatter(test, x='Area(ha)', y='Production(tonne)', color='Crop_Type')
    fig.show()


df.isna().sum()

State_Name              0
District_Name           0
Crop_Year               0
Crop                    0
Area(ha)                0
Production(tonne)    2552
Weather_Seasons         0
Crop_Type               0
dtype: int64


null_df = df[df['Production(tonne)'].isna()]
null_df


null_df.head(10)


null_df.tail(10)


sns.heatmap(df.corr(), annot=True)

<AxesSubplot:>


dummies = pd.get_dummies(df.Weather_Seasons)
dummies


dummies2 = pd.get_dummies(df.Crop_Type)
dummies2


df1_merged = pd.concat([df, dummies], axis = 'columns')
df1_merged


df_merged = pd.concat([df1_merged, dummies2], axis = 'columns')
df_merged


sns.heatmap(df_merged.corr(), cmap='BrBG', annot=True)

<AxesSubplot:>


cdf = df_merged.copy()
sns.pairplot(cdf.corr(), height = 1.5)

<seaborn.axisgrid.PairGrid at 0x2a8383d2fa0>


df_merged.to_csv('crop_production_final.csv', index = True)

	State_Name	District_Name	Crop_Year	Season	Crop	Area(ha)	Production(tonne)
1	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Arecanut	1254.00	2000.00
2	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Other Kharif pulses	2.00	1.00
3	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Rice	102.00	321.00
4	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Banana	176.00	641.00
5	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Cashewnut	720.00	165.00
6	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Coconut	18168.00	65100000.00
7	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Dry ginger	36.00	100.00
8	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Sugarcane	1.00	2.00
9	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Sweet potato	5.00	15.00
10	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Tapioca	40.00	169.00
11	Andaman and Nicobar Islands	NICOBARS	2001	Kharif	Arecanut	1254.00	2061.00
12	Andaman and Nicobar Islands	NICOBARS	2001	Kharif	Other Kharif pulses	2.00	1.00
13	Andaman and Nicobar Islands	NICOBARS	2001	Kharif	Rice	83.00	300.00
14	Andaman and Nicobar Islands	NICOBARS	2001	Whole Year	Cashewnut	719.00	192.00
15	Andaman and Nicobar Islands	NICOBARS	2001	Whole Year	Coconut	18190.00	64430000.00
16	Andaman and Nicobar Islands	NICOBARS	2001	Whole Year	Dry ginger	46.00	100.00
17	Andaman and Nicobar Islands	NICOBARS	2001	Whole Year	Sugarcane	1.00	1.00
18	Andaman and Nicobar Islands	NICOBARS	2001	Whole Year	Sweet potato	11.00	33.00
19	Andaman and Nicobar Islands	NICOBARS	2002	Kharif	Rice	189.20	510.84
20	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Arecanut	1258.00	2083.00
21	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Banana	213.00	1278.00
22	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Black pepper	63.00	13.50
23	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Cashewnut	719.00	208.00
24	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Coconut	18240.00	67490000.00
25	Andaman and Nicobar Islands	NICOBARS	2002	Whole Year	Dry chillies	413.00	28.80

	State_Name	District_Name	Crop_Year	Season	Crop	Area(ha)	Production(tonne)
0	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Arecanut	1254.00	2000.00
1	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Other Kharif pulses	2.00	1.00
2	Andaman and Nicobar Islands	NICOBARS	2000	Kharif	Rice	102.00	321.00
3	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Banana	176.00	641.00
4	Andaman and Nicobar Islands	NICOBARS	2000	Whole Year	Cashewnut	720.00	165.00
...	...	...	...	...	...	...	...
246086	West Bengal	PURULIA	2014	Summer	Rice	306.0	801.0
246087	West Bengal	PURULIA	2014	Summer	Sesamum	627.0	463.0
246088	West Bengal	PURULIA	2014	Whole Year	Sugarcane	324.0	16250.0
246089	West Bengal	PURULIA	2014	Winter	Rice	279151.0	597899.0
246090	West Bengal	PURULIA	2014	Winter	Sesamum	175.0	88.0

	Area(ha)	Production(tonne)
count	2.460910e+05	2.423610e+05
mean	1.200282e+04	5.825034e+05
std	5.052340e+04	1.706581e+07
min	4.000000e-02	0.000000e+00
25%	8.000000e+01	8.800000e+01
50%	5.820000e+02	7.290000e+02
75%	4.392000e+03	7.023000e+03
max	8.580100e+06	1.250800e+09

	Production(tonne)
count	5.000000e+00
mean	1.350256e+09
std	1.699723e+09
min	6.441377e+07
25%	1.706579e+08
50%	4.345498e+08
75%	2.051688e+09
max	4.029970e+09

	Crop_Year	Crop	Production(tonne)
0	1997	Arhar/Tur	1655931.0
1	1997	Bajra	7410795.0
2	1997	Banana	2762324.0
3	1997	Barley	1581811.0
4	1997	Black pepper	924.0
...	...	...	...
958	2015	Small millets	2911.0
959	2015	Soyabean	3190.0
960	2015	Sugarcane	577157.2
961	2015	Urad	27063.1
962	2015	Wheat	840.4

	State_Name	District_Name
0	Andaman and Nicobar Islands	203
1	Andhra Pradesh	9628
2	Arunachal Pradesh	2546
3	Assam	14628
4	Bihar	18885
5	Chandigarh	90
6	Chhattisgarh	10709
7	Dadra and Nagar Haveli	263
8	Goa	208
9	Gujarat	8436
10	Haryana	5875
11	Himachal Pradesh	2494
12	Jammu and Kashmir	1634
13	Jharkhand	1266
14	Karnataka	21122
15	Kerala	4261
16	Madhya Pradesh	22943
17	Maharashtra	12628
18	Manipur	1267
19	Meghalaya	2867
20	Mizoram	957
21	Nagaland	3906
22	Odisha	13575
23	Puducherry	876
24	Punjab	3173
25	Rajasthan	12514
26	Sikkim	714
27	Tamil Nadu	13547
28	Telangana	5649
29	Tripura	1412
30	Uttar Pradesh	33306
31	Uttarakhand	4896
32	West Bengal	9613

	State_Name	Production(tonne)
0	Andaman and Nicobar Islands	2.510869e+05
1	Andhra Pradesh	2.984922e+08
2	Arunachal Pradesh	4.298912e+06
3	Assam	1.150845e+08
4	Bihar	2.415800e+08
5	Chandigarh	4.827750e+04
6	Chhattisgarh	9.900568e+07
7	Dadra and Nagar Haveli	1.847871e+06
8	Goa	1.580998e+06
9	Gujarat	2.403215e+08
10	Haryana	2.618656e+08
11	Himachal Pradesh	1.685808e+07
12	Jammu and Kashmir	1.319469e+07
13	Jharkhand	1.068637e+07
14	Karnataka	2.384410e+08
15	Kerala	1.071412e+07
16	Madhya Pradesh	3.578921e+08
17	Maharashtra	6.103534e+08
18	Manipur	4.119722e+06
19	Meghalaya	7.734268e+06
20	Mizoram	1.254633e+06
21	Nagaland	1.152271e+07
22	Odisha	1.530753e+08
23	Puducherry	4.038461e+06
24	Punjab	4.964972e+08
25	Rajasthan	2.581434e+08
26	Sikkim	2.148563e+06
27	Tamil Nadu	1.347562e+08
28	Telangana	1.686930e+08
29	Tripura	1.112094e+07
30	Uttar Pradesh	2.373659e+09
31	Uttarakhand	3.590835e+07
32	West Bengal	5.660915e+08

	Season	Production(tonne)
0	Autumn	6.441377e+07
1	Kharif	4.029970e+09
2	Rabi	2.051688e+09
3	Summer	1.706579e+08
4	Whole Year	1.344248e+11
5	Winter	4.345498e+08

	Crop_Year	Production(tonne)
0	1997	1.965446e+08
1	1998	1.674131e+08
2	1999	1.528994e+08
3	2000	1.407050e+08
4	2001	1.492294e+08
5	2002	1.306218e+08
6	2003	1.519163e+08
7	2004	2.745188e+08
8	2005	3.020638e+08
9	2006	2.992419e+08
10	2007	2.848714e+08
11	2008	3.210495e+08
12	2009	3.371434e+08
13	2010	3.805623e+08
14	2011	3.066722e+08
15	2012	3.068063e+08
16	2013	3.330503e+08
17	2014	3.168134e+08
18	2015	6.935065e+06
19	1997	9.374314e+07
20	1998	1.222536e+08
21	1999	9.294531e+07
22	2000	9.348531e+07
23	2001	1.025934e+08
24	2002	8.631028e+07
25	2003	1.121630e+08
26	2004	1.053118e+08
27	2005	1.284176e+08
28	2006	1.173023e+08
29	2007	1.207511e+08
30	2008	1.475978e+08
31	2009	1.197610e+08
32	2010	1.788497e+08
33	2011	1.622513e+08
34	2012	1.683872e+08
35	2013	1.418905e+08
36	2014	9.820722e+07

	Crop_Year	Production(tonne)
0	1997	2.902877e+08
1	1998	2.896667e+08
2	1999	2.458447e+08
3	2000	2.341903e+08
4	2001	2.518229e+08
5	2002	2.169321e+08
6	2003	2.640792e+08
7	2004	3.798306e+08
8	2005	4.304814e+08
9	2006	4.165442e+08
10	2007	4.056225e+08
11	2008	4.686473e+08
12	2009	4.569043e+08
13	2010	5.594120e+08
14	2011	4.689235e+08
15	2012	4.751936e+08
16	2013	4.749408e+08
17	2014	4.150207e+08
18	2015	6.935065e+06

	Crop	Crop_Count
0	Arecanut	134
1	Arhar/Tur	7322
2	Bajra	5267
3	Banana	394
4	Barley	4151
...	...	...
80	Urad	9677
81	Varagu	58
82	Wheat	7844
83	other misc. pulses	70
84	other oilseeds	551

	index	Crop	Crop_Count
0	62	Rice	14976
1	38	Maize	13707
2	42	Moong(Green Gram)	10109
3	80	Urad	9677
4	25	Groundnut	8558
...	...	...	...
80	63	Ricebean (nagadal)	10
81	54	Perilla	9
82	28	Jobster	9
83	75	Tea	8
84	32	Kapas	8

	index	Crop	Crop_Count
60	45	Oilseeds total	90
61	65	Samai	87
62	77	Tomato	78
63	83	other misc. pulses	70
64	9	Cabbage	61
65	11	Cashewnut	60
66	81	Varagu	58
67	39	Mango	55
68	67	Sapota	39
69	35	Lemon	39
70	36	Lentil	31
71	56	Pome Granet	21
72	5	Bean	20
73	15	Cond-spcs other	18
74	60	Rajmash Kholar	18
75	13	Coconut	17
76	10	Cardamom	17
77	31	Jute & mesta	12
78	24	Grapes	12
79	14	Colocosia	11
80	63	Ricebean (nagadal)	10
81	54	Perilla	9
82	28	Jobster	9
83	75	Tea	8
84	32	Kapas	8

		Crop
Crop	Weather_Seasons
Arecanut	Autumn	16
Arecanut	Winter	118
Arhar/Tur	Autumn	6816
	Summer	28
	Winter	478
...	...	...
Wheat	Winter	7537
other misc. pulses	Autumn	29
other misc. pulses	Winter	41
other oilseeds	Autumn	248
other oilseeds	Winter	303

	State_Name	Crop	Production(tonne)
0	Andaman and Nicobar Islands	Arecanut	20300.0
1	Andaman and Nicobar Islands	Arhar/Tur	104.0
2	Andaman and Nicobar Islands	Black pepper	120.0
3	Andaman and Nicobar Islands	Cashewnut	310.0
4	Andaman and Nicobar Islands	Dry chillies	575.0
...	...	...	...
919	West Bengal	Small millets	42033.0
920	West Bengal	Soyabean	7009.0
921	West Bengal	Sunflower	141789.0
922	West Bengal	Urad	756330.0
923	West Bengal	Wheat	15785272.0

	Area(ha)	Crop_Type	Production(tonne)
0	0.10	Kharif	0.08
1	0.28	Kharif	0.02
2	0.50	Rabi	0.20
3	0.58	Rabi	0.31
4	0.80	Kharif	1.00
...	...	...	...
44166	3989200.00	Kharif	2899500.00
44167	4205800.00	Kharif	3183800.00
44168	5251200.00	Kharif	3519600.00
44169	5544000.00	Kharif	4485800.00
44170	8580100.00	Kharif	7556300.00

	Area(ha)	Crop_Type	Total_Production(tonne)
0	0.10	Kharif	0.08
1	0.28	Kharif	0.02
2	0.50	Rabi	0.20
3	0.58	Rabi	0.31
4	0.80	Kharif	1.00
5	0.97	Kharif	0.12
6	1.00	Kharif	6322.96
7	1.00	Rabi	1886.07
8	1.00	Zaid	1120.00
9	1.05	Rabi	0.68
10	1.29	Kharif	2.00
11	1.50	Kharif	2.26
12	1.58	Kharif	2.00
13	1.62	Rabi	1.31
14	2.00	Kharif	5663.90
15	2.00	Rabi	2938.25
16	2.00	Zaid	737.00
17	2.08	Kharif	1.00
18	2.09	Kharif	12.06
19	2.20	Rabi	1.00
20	2.50	Kharif	0.70
21	2.57	Kharif	2.00
22	2.73	Rabi	2.00
23	2.78	Kharif	2.67
24	2.82	Rabi	1.00
25	2.90	Kharif	1.90
26	3.00	Kharif	10099.74
27	3.00	Rabi	3377.91
28	3.00	Zaid	1018.00
29	3.25	Rabi	2.00

	State_Name	District_Name	Crop_Year	Crop	Area(ha)	Production(tonne)	Weather_Seasons	Crop_Type
396	Andhra Pradesh	ANANTAPUR	2007	Moong(Green Gram)	1000.0	NaN	Autumn	Kharif
403	Andhra Pradesh	ANANTAPUR	2007	Horse-gram	1000.0	NaN	Winter	Kharif
463	Andhra Pradesh	ANANTAPUR	2009	Rapeseed &Mustard	8.0	NaN	Winter	Rabi
480	Andhra Pradesh	ANANTAPUR	2010	Other Kharif pulses	1.0	NaN	Autumn	Kharif
875	Andhra Pradesh	CHITTOOR	2001	Wheat	4.0	NaN	Winter	Rabi
...	...	...	...	...	...	...	...	...
187317	West Bengal	MEDINIPUR WEST	2010	Peas & beans (Pulses)	2.0	NaN	Winter	Rabi
187697	West Bengal	MURSHIDABAD	2006	Moong(Green Gram)	200.0	NaN	Autumn	Kharif
188554	West Bengal	PURULIA	2001	Rapeseed &Mustard	427.0	NaN	Winter	Rabi
188585	West Bengal	PURULIA	2002	Rapeseed &Mustard	522.0	NaN	Winter	Rabi
188761	West Bengal	PURULIA	2008	Khesari	2.0	NaN	Winter	Rabi

	State_Name	District_Name	Crop_Year	Crop	Area(ha)	Production(tonne)	Weather_Seasons	Crop_Type
182562	West Bengal	BARDHAMAN	2005	Moong(Green Gram)	1.0	NaN	Summer	Kharif
182579	West Bengal	BARDHAMAN	2006	Linseed	2.0	NaN	Winter	Rabi
185275	West Bengal	HOOGHLY	2008	Arhar/Tur	1.0	NaN	Winter	Kharif
185882	West Bengal	JALPAIGURI	2004	Linseed	878.0	NaN	Winter	Rabi
187053	West Bengal	MEDINIPUR WEST	2001	Masoor	134.0	NaN	Winter	Rabi
187317	West Bengal	MEDINIPUR WEST	2010	Peas & beans (Pulses)	2.0	NaN	Winter	Rabi
187697	West Bengal	MURSHIDABAD	2006	Moong(Green Gram)	200.0	NaN	Autumn	Kharif
188554	West Bengal	PURULIA	2001	Rapeseed &Mustard	427.0	NaN	Winter	Rabi
188585	West Bengal	PURULIA	2002	Rapeseed &Mustard	522.0	NaN	Winter	Rabi
188761	West Bengal	PURULIA	2008	Khesari	2.0	NaN	Winter	Rabi

	Autumn	Summer	Winter
0	1	0	0
1	1	0	0
2	1	0	0
3	1	0	0
4	1	0	0
...	...	...	...
188968	0	1	0
188969	0	1	0
188970	0	1	0
188971	0	0	1
188972	0	0	1

Personal Challenge¶

Challenge description:¶

Challenge predictive goal:¶

Student Information:¶

Data set information¶

Finding(s)¶

Finding the datatype for each column in this dataset¶

Getting statistical data about each column¶

Getting the number of districts per state¶

Visualization of the top 20 states with the highest amount of districts¶

Hypothesis¶

Findings(s)¶

Conclusion:¶

Getting amount of crops produced per season,¶

Finding(s)¶

Solution¶

Printing out the value whole year from the season column¶

Finding(s)¶

Solution¶

Retrying getting amount of crops produced per season.¶

Removing whole year season from amount_crops_produced_per_season column¶

Graphical Representaiton showing total amount of crops produced per season¶

Removal of whole year column from main dataset¶

Getting total amount of crops produced per year¶

Finding(s)¶

Finding out why the Crop_Year column does not group by properly¶

(1) Hypothesis of problem: Crop_year column values ar enot of the same datatype¶

Conclusion¶

(2) Hypothesis of problem: Crop_year column values are not unique¶

Conclusion¶

Solution of why Crop_Year column does not group by properly¶

Conclusion¶

Continuation:¶

Getting statistical data about each column¶

Getting total amount of crops produced per year¶

Visualization of total amount of crops produced per year¶

Finding(s)¶

Finding(s)¶

For each year show the total amount of crops that were produced and the name of the crop¶

Matplotlib plot¶

Visualization of total amount of crops produced per thousands for each year¶

Hypothesis:¶

Plotly plot¶

Visualizaiton of total amount(million) of crops produced per crop for each year¶

Visualization of total amount(thousand) of crops produced per crop for each year¶

Getting the most popular and least crops recorded in this dataset¶

Ordering the crop count dataframe by crop_count column to see the top crops in this dataset¶

Visualization of entire Crop-Count¶

Explanation of newly generated column crop_count:¶

Getting top 25 popular Crops¶

Visualization of top 25 popular crops¶

Using squarify to visualize the 25 most popular crops¶

Finding(s) before removal of whole year season¶

Finding(s) after removal of whole year season data¶

Getting least 25 Crop_Count¶

Visualization of the 25 least popular crops¶

Finding(s):¶

For the top 25 crops I want to find out when each crop had the most yield¶

Getting for each of the 25 top crops when was their best yield season¶

Seaborn plot¶

Plotly plot¶

Finding(s)¶

Data transformation of seasons in the dataset¶

Creation of new columns called Crop type and Weather seasons¶

Replotting getting for each of the 25 top crops when was their best yield season¶

Finding(s)¶

Best yield seasons for the 25 most popular crops that amount produced reached billion¶

Best yield seasons for the 25 most popular crops that amount produced reached million but not billion¶

Best yield seasons for the 25 most popular crops that amount produced reached thousands but not million or billion¶

For each state what is the total amount produced for crops produced by that state¶

Getting total amount of crops produced per each state¶

Visualization showing for each state the total amount produced for crops they produce¶

Finding(s):¶

Finding a relationship between Area and Production¶

Hypothesis:¶

Getting the top 30 data entries¶

Visualization of how much was produced depending on the area of land used for each crop_type¶

Intial graphical representation¶

Visualization of how much was produced per state depending on the area of land used for each crop_type¶

EDA next step¶